ali-issa/arb_tokenized_filtered_dataset_with_eng-bpe-tokenizer-32768 Viewer • Updated 3 days ago • 142M • 3
ali-issa/arb_tokenized_filtered_dataset_with_eng-bpe-tokenizer-32768 Viewer • Updated 3 days ago • 142M • 3
ali-issa/arb_filtered_short_sentences_less_than_5_words_training_data_for_opus_aya_xnli Updated 10 days ago • 47
ali-issa/eng_filtered_short_sentences_less_than_5_words_training_data_for_opus_aya_xnli Updated 13 days ago • 9
view article Article Efficient LLM Pretraining: Packed Sequences and Masked Attention By sirluk • Oct 7, 2024 • 14